Arize-ai/phoenix: AI Observability & Evaluation

English · 简体中文

Arize Phoenix is Arize's open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. For managed production workflows, Arize also offers Arize AX. Phoenix provides:

_Tracing_ - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
_Evaluation_ - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
_Datasets_ - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
_Experiments_ - Track and evaluate changes to prompts, LLMs, and retrieval.
_Playground_- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
_Prompt Management_- Manage and test prompt changes systematically using version control, tagging, and experimentation.
_PXI (Phoenix Intelligence)_ - An AI engineering agent built into Phoenix for debugging traces, iterating on prompts, and navigating the product.
_Remote MCP Server_ - Connect Claude Code, Cursor, and other MCP clients directly to your Phoenix instance's /mcp endpoint to query traces, datasets, experiments, and more.

Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (OpenAI Agents SDK, Claude Agent SDK, LangGraph, Vercel AI SDK, Mastra, CrewAI, LlamaIndex, DSPy) and LLM providers (OpenAI, Anthropic, Google GenAI, Google ADK, AWS Bedrock, OpenRouter, LiteLLM, and more). For details on auto-instrumentation, check out the OpenInference project.

Phoenix runs practically anywhere, including your local machine, a containerized deployment, or in the cloud. See Environments for a walkthrough of each option, or jump straight into the Tracing Quickstart.

[!NOTE]

Phoenix is open-source and self-hosted. For a managed platform, Arize offers Arize AX — the same OpenTelemetry/OpenInference instrumentation works with both. See the full comparison.

Run Locally
Trace Your Application
Deploy
Packages
Tracing Integrations
Sandboxes
For Humans and Coding Agents
Security & Privacy
Community

Run Locally

Install Phoenix via pip or conda and have a fully functional Phoenix. For all installation and hosting options, see the install guide.

pip install arize-phoenix
phoenix serve

Or run it with no install using uvx:

uvx arize-phoenix serve

Trace Your Application

The fastest way to send traces is to let your coding agent (Claude Code, Codex, Cursor, and others) instrument your app. From your project directory, run:

npx @arizeai/phoenix-cli setup
or, with Phoenix installed: px setup

Setup detects your framework and LLM provider, installs the right OpenInference instrumentation, and wires up trace export. Prefer to wire it up in code? See the tracing documentation.

Deploy

Phoenix container images are available via Docker Hub and can be deployed using Docker or Kubernetes via the Helm chart.

For Docker Compose, Kubernetes/Helm, and other deployment options, see the self-hosting documentation.

[!NOTE]

The Google Cloud button builds Phoenix from source in Cloud Shell rather than deploying the prebuilt Docker Hub image. The Azure template serves plain HTTP (Azure Container Instances does not terminate TLS) — front it with a TLS proxy such as an Application Gateway before production use.

Packages

The arize-phoenix package includes the entire Phoenix platform. However, if you have deployed the Phoenix platform, there are lightweight Python sub-packages and TypeScript packages that can be used in conjunction with the platform.

Python Subpackages

| Package | Version & Docs | Description | | --------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ | | arize-phoenix-otel | Docs</a> | Provides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults | | arize-phoenix-client | | Lightweight client for interacting with the Phoenix server via its OpenAPI REST interface | | arize-phoenix-evals | | Tooling to evaluate LLM applications including RAG relevance, answer relevance, and more |

TypeScript Subpackages

Tracing Integrations

Phoenix is built on top of OpenTelemetry and is vendor, language, and framework agnostic. For details about tracing integrations and example applications, see the OpenInference project and the integrations documentation.

Python Integrations | | Integration | Package | Version | |:---:|---|---|---| | | OpenAI | openinference-instrumentation-openai | PyPI Version</a> | | | OpenAI Agents | openinference-instrumentation-openai-agents | | | | LlamaIndex | openinference-instrumentation-llama-index | | | | DSPy | openinference-instrumentation-dspy | | | | AWS Bedrock | openinference-instrumentation-bedrock | | | | LangChain | openinference-instrumentation-langchain | PyPI Version</a> | | | LangGraph | openinference-instrumentation-langchain | | | | MistralAI | openinference-instrumentation-mistralai | | | | Cohere | openinference-instrumentation-cohere | | | | Together AI | openinference-instrumentation-together | | | | Ollama | openinference-instrumentation-ollama | PyPI Version</a> | | | Google GenAI | openinference-instrumentation-google-genai | | | | Google ADK | openinference-instrumentation-google-adk | | | | Guardrails | openinference-instrumentation-guardrails | | | | VertexAI | openinference-instrumentation-vertexai | | | | CrewAI | openinference-instrumentation-crewai | PyPI Version</a> | | | Haystack | openinference-instrumentation-haystack | | | | LiteLLM | openinference-instrumentation-litellm | | | | OpenRouter | openinference-instrumentation-openai | | | | OrcaRouter | openinference-instrumentation-openai | | | | Groq | openinference-instrumentation-groq | PyPI Version</a> | | | Instructor | openinference-instrumentation-instructor | | | | Anthropic | openinference-instrumentation-anthropic | | | | Smolagents | openinference-instrumentation-smolagents | | | | Agno | openinference-instrumentation-agno | | | | BeeAI | openinference-instrumentation-beeai | PyPI Version</a> | | | Strands Agents | openinference-instrumentation-strands-agents | | | | Restate | openinference-instrumentation-openai-agents | | | | MCP | openinference-instrumentation-mcp | | | | Pydantic AI | openinference-instrumentation-pydantic-ai | | | | AG2 | openinference-instrumentation-ag2 | PyPI Version</a> | | | Autogen AgentChat | openinference-instrumentation-autogen-agentchat | | | | Portkey | openinference-instrumentation-portkey | | | | Agent Spec | openinference-instrumentation-agentspec | | | | Claude Agent SDK | openinference-instrumentation-claude-agent-sdk | |